| |
Records |
Links |
|
Author |
Axel Barroso-Laguna; Edgar Riba; Daniel Ponsa; Krystian Mikolajczyk |
|
| |
Title |
Key.Net: Keypoint Detection by Handcrafted and Learned CNN Filters |
Type |
Conference Article |
| |
Year |
2019 |
Publication  |
18th IEEE International Conference on Computer Vision |
Abbreviated Journal |
|
|
| |
Volume |
|
Issue |
|
Pages |
5835-5843 |
|
| |
Keywords |
|
|
| |
Abstract |
We introduce a novel approach for keypoint detection task that combines handcrafted and learned CNN filters within a shallow multi-scale architecture. Handcrafted filters provide anchor structures for learned filters, which localize, score and rank repeatable features. Scale-space representation is used within the network to extract keypoints at different levels. We design a loss function to detect robust features that exist across a range of scales and to maximize the repeatability score. Our Key.Net model is trained on data synthetically created from ImageNet and evaluated on HPatches benchmark. Results show that our approach outperforms state-of-the-art detectors in terms of repeatability, matching performance and complexity. |
|
| |
Address |
Seul; Corea; October 2019 |
|
| |
Corporate Author |
|
Thesis |
|
|
| |
Publisher |
|
Place of Publication |
|
Editor |
|
|
| |
Language |
|
Summary Language |
|
Original Title |
|
|
| |
Series Editor |
|
Series Title |
|
Abbreviated Series Title |
|
|
| |
Series Volume |
|
Series Issue |
|
Edition |
|
|
| |
ISSN |
|
ISBN |
|
Medium |
|
|
| |
Area |
|
Expedition |
|
Conference |
ICCV |
|
| |
Notes |
MSIAU; 600.122 |
Approved |
no |
|
| |
Call Number |
Admin @ si @ BRP2019 |
Serial |
3290 |
|
| Permanent link to this record |
| |
|
| |
|
Author |
Hamed H. Aghdam; Abel Gonzalez-Garcia; Joost Van de Weijer; Antonio Lopez |
|
| |
Title |
Active Learning for Deep Detection Neural Networks |
Type |
Conference Article |
| |
Year |
2019 |
Publication |
18th IEEE International Conference on Computer Vision |
Abbreviated Journal |
|
|
| |
Volume |
|
Issue |
|
Pages |
3672-3680 |
|
| |
Keywords |
|
|
| |
Abstract |
The cost of drawing object bounding boxes (ie labeling) for millions of images is prohibitively high. For instance, labeling pedestrians in a regular urban image could take 35 seconds on average. Active learning aims to reduce the cost of labeling by selecting only those images that are informative to improve the detection network accuracy. In this paper, we propose a method to perform active learning of object detectors based on convolutional neural networks. We propose a new image-level scoring process to rank unlabeled images for their automatic selection, which clearly outperforms classical scores. The proposed method can be applied to videos and sets of still images. In the former case, temporal selection rules can complement our scoring process. As a relevant use case, we extensively study the performance of our method on the task of pedestrian detection. Overall, the experiments show that the proposed method performs better than random selection. |
|
| |
Address |
Seul; Korea; October 2019 |
|
| |
Corporate Author |
|
Thesis |
|
|
| |
Publisher |
|
Place of Publication |
|
Editor |
|
|
| |
Language |
|
Summary Language |
|
Original Title |
|
|
| |
Series Editor |
|
Series Title |
|
Abbreviated Series Title |
|
|
| |
Series Volume |
|
Series Issue |
|
Edition |
|
|
| |
ISSN |
|
ISBN |
|
Medium |
|
|
| |
Area |
|
Expedition |
|
Conference |
ICCV |
|
| |
Notes |
ADAS; LAMP; 600.124; 600.109; 600.141; 600.120; 600.118 |
Approved |
no |
|
| |
Call Number |
Admin @ si @ AGW2019 |
Serial |
3321 |
|
| Permanent link to this record |
| |
|
| |
|
Author |
Felipe Codevilla; Eder Santana; Antonio Lopez; Adrien Gaidon |
|
| |
Title |
Exploring the Limitations of Behavior Cloning for Autonomous Driving |
Type |
Conference Article |
| |
Year |
2019 |
Publication |
18th IEEE International Conference on Computer Vision |
Abbreviated Journal |
|
|
| |
Volume |
|
Issue |
|
Pages |
9328-9337 |
|
| |
Keywords |
|
|
| |
Abstract |
Driving requires reacting to a wide variety of complex environment conditions and agent behaviors. Explicitly modeling each possible scenario is unrealistic. In contrast, imitation learning can, in theory, leverage data from large fleets of human-driven cars. Behavior cloning in particular has been successfully used to learn simple visuomotor policies end-to-end, but scaling to the full spectrum of driving behaviors remains an unsolved problem. In this paper, we propose a new benchmark to experimentally investigate the scalability and limitations of behavior cloning. We show that behavior cloning leads to state-of-the-art results, executing complex lateral and longitudinal maneuvers, even in unseen environments, without being explicitly programmed to do so. However, we confirm some limitations of the behavior cloning approach: some well-known limitations (eg, dataset bias and overfitting), new generalization issues (eg, dynamic objects and the lack of a causal modeling), and training instabilities, all requiring further research before behavior cloning can graduate to real-world driving. The code, dataset, benchmark, and agent studied in this paper can be found at github. |
|
| |
Address |
Seul; Korea; October 2019 |
|
| |
Corporate Author |
|
Thesis |
|
|
| |
Publisher |
|
Place of Publication |
|
Editor |
|
|
| |
Language |
|
Summary Language |
|
Original Title |
|
|
| |
Series Editor |
|
Series Title |
|
Abbreviated Series Title |
|
|
| |
Series Volume |
|
Series Issue |
|
Edition |
|
|
| |
ISSN |
|
ISBN |
|
Medium |
|
|
| |
Area |
|
Expedition |
|
Conference |
ICCV |
|
| |
Notes |
ADAS; 600.124; 600.118 |
Approved |
no |
|
| |
Call Number |
Admin @ si @ CSL2019 |
Serial |
3322 |
|
| Permanent link to this record |
| |
|
| |
|
Author |
David Berga; Xose R. Fernandez-Vidal; Xavier Otazu; Xose M. Pardo |
|
| |
Title |
SID4VAM: A Benchmark Dataset with Synthetic Images for Visual Attention Modeling |
Type |
Conference Article |
| |
Year |
2019 |
Publication |
18th IEEE International Conference on Computer Vision |
Abbreviated Journal |
|
|
| |
Volume |
|
Issue |
|
Pages |
8788-8797 |
|
| |
Keywords |
|
|
| |
Abstract |
A benchmark of saliency models performance with a synthetic image dataset is provided. Model performance is evaluated through saliency metrics as well as the influence of model inspiration and consistency with human psychophysics. SID4VAM is composed of 230 synthetic images, with known salient regions. Images were generated with 15 distinct types of low-level features (e.g. orientation, brightness, color, size...) with a target-distractor popout type of synthetic patterns. We have used Free-Viewing and Visual Search task instructions and 7 feature contrasts for each feature category. Our study reveals that state-ofthe-art Deep Learning saliency models do not perform well with synthetic pattern images, instead, models with Spectral/Fourier inspiration outperform others in saliency metrics and are more consistent with human psychophysical experimentation. This study proposes a new way to evaluate saliency models in the forthcoming literature, accounting for synthetic images with uniquely low-level feature contexts, distinct from previous eye tracking image datasets. |
|
| |
Address |
Seul; Corea; October 2019 |
|
| |
Corporate Author |
|
Thesis |
|
|
| |
Publisher |
|
Place of Publication |
|
Editor |
|
|
| |
Language |
|
Summary Language |
|
Original Title |
|
|
| |
Series Editor |
|
Series Title |
|
Abbreviated Series Title |
|
|
| |
Series Volume |
|
Series Issue |
|
Edition |
|
|
| |
ISSN |
|
ISBN |
|
Medium |
|
|
| |
Area |
|
Expedition |
|
Conference |
ICCV |
|
| |
Notes |
NEUROBIT; 600.128 |
Approved |
no |
|
| |
Call Number |
Admin @ si @ BFO2019b |
Serial |
3372 |
|
| Permanent link to this record |
| |
|
| |
|
Author |
Mohammad Rouhani; Angel Sappa |
|
| |
Title |
Implicit B-Spline Fitting Using the 3L Algorithm |
Type |
Conference Article |
| |
Year |
2011 |
Publication |
18th IEEE International Conference on Image Processing |
Abbreviated Journal |
|
|
| |
Volume |
|
Issue |
|
Pages |
893-896 |
|
| |
Keywords |
|
|
| |
Abstract |
|
|
| |
Address |
Brussels, Belgium |
|
| |
Corporate Author |
|
Thesis |
|
|
| |
Publisher |
|
Place of Publication |
|
Editor |
|
|
| |
Language |
|
Summary Language |
|
Original Title |
|
|
| |
Series Editor |
|
Series Title |
|
Abbreviated Series Title |
|
|
| |
Series Volume |
|
Series Issue |
|
Edition |
|
|
| |
ISSN |
|
ISBN |
|
Medium |
|
|
| |
Area |
|
Expedition |
|
Conference |
ICIP |
|
| |
Notes |
ADAS |
Approved |
no |
|
| |
Call Number |
Admin @ si @ RoS2011a; ADAS @ adas @ |
Serial |
1782 |
|
| Permanent link to this record |
| |
|
| |
|
Author |
Eduardo Aguilar; Petia Radeva |
|
| |
Title |
Class-Conditional Data Augmentation Applied to Image Classification |
Type |
Conference Article |
| |
Year |
2019 |
Publication |
18th International Conference on Computer Analysis of Images and Patterns |
Abbreviated Journal |
|
|
| |
Volume |
11679 |
Issue |
|
Pages |
182-192 |
|
| |
Keywords |
CNNs; Data augmentation; Deep learning; Epistemic uncertainty; Image classification; Food recognition |
|
| |
Abstract |
Image classification is widely researched in the literature, where models based on Convolutional Neural Networks (CNNs) have provided better results. When data is not enough, CNN models tend to be overfitted. To deal with this, often, traditional techniques of data augmentation are applied, such as: affine transformations, adjusting the color balance, among others. However, we argue that some techniques of data augmentation may be more appropriate for some of the classes. In order to select the techniques that work best for particular class, we propose to explore the epistemic uncertainty for the samples within each class. From our experiments, we can observe that when the data augmentation is applied class-conditionally, we improve the results in terms of accuracy and also reduce the overall epistemic uncertainty. To summarize, in this paper we propose a class-conditional data augmentation procedure that allows us to obtain better results and improve robustness of the classification in the face of model uncertainty. |
|
| |
Address |
Salermo; Italy; September 2019 |
|
| |
Corporate Author |
|
Thesis |
|
|
| |
Publisher |
|
Place of Publication |
|
Editor |
|
|
| |
Language |
|
Summary Language |
|
Original Title |
|
|
| |
Series Editor |
|
Series Title |
|
Abbreviated Series Title |
LNCS |
|
| |
Series Volume |
|
Series Issue |
|
Edition |
|
|
| |
ISSN |
|
ISBN |
|
Medium |
|
|
| |
Area |
|
Expedition |
|
Conference |
CAIP |
|
| |
Notes |
MILAB; no proj |
Approved |
no |
|
| |
Call Number |
Admin @ si @ AgR2019 |
Serial |
3366 |
|
| Permanent link to this record |
| |
|
| |
|
Author |
Estefania Talavera; Nicolai Petkov; Petia Radeva |
|
| |
Title |
Unsupervised Routine Discovery in Egocentric Photo-Streams |
Type |
Conference Article |
| |
Year |
2019 |
Publication |
18th International Conference on Computer Analysis of Images and Patterns |
Abbreviated Journal |
|
|
| |
Volume |
11678 |
Issue |
|
Pages |
576-588 |
|
| |
Keywords |
Routine discovery; Lifestyle; Egocentric vision; Behaviour analysis |
|
| |
Abstract |
The routine of a person is defined by the occurrence of activities throughout different days, and can directly affect the person’s health. In this work, we address the recognition of routine related days. To do so, we rely on egocentric images, which are recorded by a wearable camera and allow to monitor the life of the user from a first-person view perspective. We propose an unsupervised model that identifies routine related days, following an outlier detection approach. We test the proposed framework over a total of 72 days in the form of photo-streams covering around 2 weeks of the life of 5 different camera wearers. Our model achieves an average of 76% Accuracy and 68% Weighted F-Score for all the users. Thus, we show that our framework is able to recognise routine related days and opens the door to the understanding of the behaviour of people. |
|
| |
Address |
Salermo; Italy; September 2019 |
|
| |
Corporate Author |
|
Thesis |
|
|
| |
Publisher |
|
Place of Publication |
|
Editor |
|
|
| |
Language |
|
Summary Language |
|
Original Title |
|
|
| |
Series Editor |
|
Series Title |
|
Abbreviated Series Title |
LNCS |
|
| |
Series Volume |
|
Series Issue |
|
Edition |
|
|
| |
ISSN |
|
ISBN |
|
Medium |
|
|
| |
Area |
|
Expedition |
|
Conference |
CAIP |
|
| |
Notes |
MILAB; no proj |
Approved |
no |
|
| |
Call Number |
Admin @ si @ TPR2019a |
Serial |
3367 |
|
| Permanent link to this record |
| |
|
| |
|
Author |
Fernando Vilariño; Panagiota Spyridonos; Jordi Vitria; Fernando Azpiroz; Petia Radeva |
|
| |
Title |
Automatic Detection of Intestinal Juices in Wireless Capsule Video Endoscopy |
Type |
Conference Article |
| |
Year |
2006 |
Publication |
18th International Conference on Pattern Recognition |
Abbreviated Journal |
|
|
| |
Volume |
4 |
Issue |
|
Pages |
719-722 |
|
| |
Keywords |
Clinical diagnosis , Endoscopes , Fluids and secretions , Gabor filters , Hospitals , Image sequence analysis , Intestines , Lighting , Shape , Visualization |
|
| |
Abstract |
Wireless capsule video endoscopy is a novel and challenging clinical technique, whose major reported drawback relates to the high amount of time needed for video visualization. In this paper, we propose a method for the rejection of the parts of the video resulting not valid for analysis by means of automatic detection of intestinal juices. We applied Gabor filters for the characterization of the bubble-like shape of intestinal juices in fasting patients. Our method achieves a significant reduction in visualization time, with no relevant loss of valid frames. The proposed approach is easily extensible to other image analysis scenarios where the described pattern of bubbles can be found. |
|
| |
Address |
Hong Kong |
|
| |
Corporate Author |
|
Thesis |
|
|
| |
Publisher |
|
Place of Publication |
|
Editor |
|
|
| |
Language |
|
Summary Language |
|
Original Title |
|
|
| |
Series Editor |
|
Series Title |
|
Abbreviated Series Title |
|
|
| |
Series Volume |
|
Series Issue |
|
Edition |
|
|
| |
ISSN |
1051-4651 |
ISBN |
0-7695-2521-0 |
Medium |
|
|
| |
Area |
800 |
Expedition |
|
Conference |
ICPR |
|
| |
Notes |
MV;OR;MILAB;SIAI |
Approved |
no |
|
| |
Call Number |
BCNPCL @ bcnpcl @ VSV2006b; IAM @ iam @ VSV2006g |
Serial |
727 |
|
| Permanent link to this record |
| |
|
| |
|
Author |
Joan Mas; B. Lamiroy; Gemma Sanchez; Josep Llados |
|
| |
Title |
Automatic Adjacency Grammar Generation from User Drawn Sketches |
Type |
Miscellaneous |
| |
Year |
2006 |
Publication |
18th International Conference on Pattern Recognition (ICPR´06), 2: 1026–1029 |
Abbreviated Journal |
|
|
| |
Volume |
|
Issue |
|
Pages |
|
|
| |
Keywords |
|
|
| |
Abstract |
|
|
| |
Address |
Hong Kong |
|
| |
Corporate Author |
|
Thesis |
|
|
| |
Publisher |
|
Place of Publication |
|
Editor |
|
|
| |
Language |
|
Summary Language |
|
Original Title |
|
|
| |
Series Editor |
|
Series Title |
|
Abbreviated Series Title |
|
|
| |
Series Volume |
|
Series Issue |
|
Edition |
|
|
| |
ISSN |
|
ISBN |
|
Medium |
|
|
| |
Area |
|
Expedition |
|
Conference |
|
|
| |
Notes |
DAG |
Approved |
no |
|
| |
Call Number |
DAG @ dag @ MLS2006a |
Serial |
709 |
|
| Permanent link to this record |
| |
|
| |
|
Author |
Oriol Ramos Terrades; Salvatore Tabbone; Ernest Valveny |
|
| |
Title |
Combination of shape descriptors using an adaptation of boosting |
Type |
Miscellaneous |
| |
Year |
2006 |
Publication |
18th International Conference on Pattern Recognition (ICPR´06), 2: 764–767 |
Abbreviated Journal |
|
|
| |
Volume |
|
Issue |
|
Pages |
|
|
| |
Keywords |
|
|
| |
Abstract |
|
|
| |
Address |
Hong Kong |
|
| |
Corporate Author |
|
Thesis |
|
|
| |
Publisher |
|
Place of Publication |
|
Editor |
|
|
| |
Language |
|
Summary Language |
|
Original Title |
|
|
| |
Series Editor |
|
Series Title |
|
Abbreviated Series Title |
|
|
| |
Series Volume |
|
Series Issue |
|
Edition |
|
|
| |
ISSN |
|
ISBN |
|
Medium |
|
|
| |
Area |
|
Expedition |
|
Conference |
|
|
| |
Notes |
DAG |
Approved |
no |
|
| |
Call Number |
DAG @ dag @ RTV2006 |
Serial |
718 |
|
| Permanent link to this record |
| |
|
| |
|
Author |
Sergio Escalera; Oriol Pujol; Petia Radeva |
|
| |
Title |
ECOC-ONE: A novel coding and decoding strategy |
Type |
Miscellaneous |
| |
Year |
2006 |
Publication |
18th International Conference on Pattern Recognition (ICPR´06), 3: 578–581, ISBN: 0–7695–2521–0 |
Abbreviated Journal |
|
|
| |
Volume |
|
Issue |
|
Pages |
|
|
| |
Keywords |
|
|
| |
Abstract |
|
|
| |
Address |
Hong Kong |
|
| |
Corporate Author |
|
Thesis |
|
|
| |
Publisher |
|
Place of Publication |
|
Editor |
|
|
| |
Language |
|
Summary Language |
|
Original Title |
|
|
| |
Series Editor |
|
Series Title |
|
Abbreviated Series Title |
|
|
| |
Series Volume |
|
Series Issue |
|
Edition |
|
|
| |
ISSN |
|
ISBN |
|
Medium |
|
|
| |
Area |
|
Expedition |
|
Conference |
|
|
| |
Notes |
MILAB;HuPBA |
Approved |
no |
|
| |
Call Number |
BCNPCL @ bcnpcl @ EPR2006b |
Serial |
693 |
|
| Permanent link to this record |
| |
|
| |
|
Author |
Sergio Escalera; Oriol Pujol; Petia Radeva |
|
| |
Title |
Boosted Landmarks of Contextual Descriptors and Forest-ECOC: a novel framework to detect and classify objects in cluttered scenes |
Type |
Miscellaneous |
| |
Year |
2006 |
Publication |
18th International Conference on Pattern Recognition (ICPR´06), 4: 104–107, ISBN: 0–7695–2521–0 |
Abbreviated Journal |
|
|
| |
Volume |
|
Issue |
|
Pages |
|
|
| |
Keywords |
|
|
| |
Abstract |
|
|
| |
Address |
Hong Kong |
|
| |
Corporate Author |
|
Thesis |
|
|
| |
Publisher |
|
Place of Publication |
|
Editor |
|
|
| |
Language |
|
Summary Language |
|
Original Title |
|
|
| |
Series Editor |
|
Series Title |
|
Abbreviated Series Title |
|
|
| |
Series Volume |
|
Series Issue |
|
Edition |
|
|
| |
ISSN |
|
ISBN |
|
Medium |
|
|
| |
Area |
|
Expedition |
|
Conference |
|
|
| |
Notes |
MILAB;HuPBA |
Approved |
no |
|
| |
Call Number |
BCNPCL @ bcnpcl @ EPR2006a |
Serial |
692 |
|
| Permanent link to this record |
| |
|
| |
|
Author |
Fadi Dornaika; Franck Davoine |
|
| |
Title |
Facial expression recognition using auto-regressive models |
Type |
Miscellaneous |
| |
Year |
2006 |
Publication |
18th International Conference on Pattern Recognition (ICPR´06), ISBN: 0–7695–2521–0, 4: 520–523 |
Abbreviated Journal |
|
|
| |
Volume |
|
Issue |
|
Pages |
|
|
| |
Keywords |
|
|
| |
Abstract |
|
|
| |
Address |
Hong Kong |
|
| |
Corporate Author |
|
Thesis |
|
|
| |
Publisher |
|
Place of Publication |
|
Editor |
|
|
| |
Language |
|
Summary Language |
|
Original Title |
|
|
| |
Series Editor |
|
Series Title |
|
Abbreviated Series Title |
|
|
| |
Series Volume |
|
Series Issue |
|
Edition |
|
|
| |
ISSN |
|
ISBN |
|
Medium |
|
|
| |
Area |
|
Expedition |
|
Conference |
|
|
| |
Notes |
|
Approved |
no |
|
| |
Call Number |
Admin @ si @ DoD2006a |
Serial |
734 |
|
| Permanent link to this record |
| |
|
| |
|
Author |
Michael Villamizar; A. Sanfeliu; Juan Andrade |
|
| |
Title |
Computation of Rotation Local Invariant Features using the Integral Image for Real Time Object Detection |
Type |
Miscellaneous |
| |
Year |
2006 |
Publication |
18th International Conference on Pattern Recognition, 81–85 |
Abbreviated Journal |
|
|
| |
Volume |
|
Issue |
|
Pages |
|
|
| |
Keywords |
|
|
| |
Abstract |
|
|
| |
Address |
Hong Kong |
|
| |
Corporate Author |
|
Thesis |
|
|
| |
Publisher |
|
Place of Publication |
|
Editor |
|
|
| |
Language |
|
Summary Language |
|
Original Title |
|
|
| |
Series Editor |
|
Series Title |
|
Abbreviated Series Title |
|
|
| |
Series Volume |
|
Series Issue |
|
Edition |
|
|
| |
ISSN |
|
ISBN |
|
Medium |
|
|
| |
Area |
|
Expedition |
|
Conference |
|
|
| |
Notes |
|
Approved |
no |
|
| |
Call Number |
Admin @ si @ VSA2006a |
Serial |
663 |
|
| Permanent link to this record |
| |
|
| |
|
Author |
Angel Morera; Angel Sanchez; Angel Sappa; Jose F. Velez |
|
| |
Title |
Robust Detection of Outdoor Urban Advertising Panels in Static Images |
Type |
Conference Article |
| |
Year |
2019 |
Publication |
18th International Conference on Practical Applications of Agents and Multi-Agent Systems |
Abbreviated Journal |
|
|
| |
Volume |
|
Issue |
|
Pages |
246-256 |
|
| |
Keywords |
Object detection; Urban ads panels; Deep learning; Single Shot Detector (SSD) architecture; Intersection over Union (IoU) metric; Augmented Reality |
|
| |
Abstract |
One interesting publicity application for Smart City environments is recognizing brand information contained in urban advertising panels. For such a purpose, a previous stage is to accurately detect and locate the position of these panels in images. This work presents an effective solution to this problem using a Single Shot Detector (SSD) based on a deep neural network architecture that minimizes the number of false detections under multiple variable conditions regarding the panels and the scene. Achieved experimental results using the Intersection over Union (IoU) accuracy metric make this proposal applicable in real complex urban images. |
|
| |
Address |
Aquila; Italia; June 2019 |
|
| |
Corporate Author |
|
Thesis |
|
|
| |
Publisher |
|
Place of Publication |
|
Editor |
|
|
| |
Language |
|
Summary Language |
|
Original Title |
|
|
| |
Series Editor |
|
Series Title |
|
Abbreviated Series Title |
|
|
| |
Series Volume |
|
Series Issue |
|
Edition |
|
|
| |
ISSN |
|
ISBN |
|
Medium |
|
|
| |
Area |
|
Expedition |
|
Conference |
PAAMS |
|
| |
Notes |
MSIAU; 600.130; 600.122 |
Approved |
no |
|
| |
Call Number |
Admin @ si @ MSS2019 |
Serial |
3270 |
|
| Permanent link to this record |
